/**
* Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
* SPDX-License-Identifier: Apache-2.0.
*/
#pragma once
#include A serializer to use for converting data to the ORC format before storing it
* in Amazon S3. For more information, see Apache ORC.See Also:
* AWS
* API Reference
The number of bytes in each stripe. The default is 64 MiB and the minimum is * 8 MiB.
*/ inline int GetStripeSizeBytes() const{ return m_stripeSizeBytes; } /** *The number of bytes in each stripe. The default is 64 MiB and the minimum is * 8 MiB.
*/ inline bool StripeSizeBytesHasBeenSet() const { return m_stripeSizeBytesHasBeenSet; } /** *The number of bytes in each stripe. The default is 64 MiB and the minimum is * 8 MiB.
*/ inline void SetStripeSizeBytes(int value) { m_stripeSizeBytesHasBeenSet = true; m_stripeSizeBytes = value; } /** *The number of bytes in each stripe. The default is 64 MiB and the minimum is * 8 MiB.
*/ inline OrcSerDe& WithStripeSizeBytes(int value) { SetStripeSizeBytes(value); return *this;} /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline int GetBlockSizeBytes() const{ return m_blockSizeBytes; } /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline bool BlockSizeBytesHasBeenSet() const { return m_blockSizeBytesHasBeenSet; } /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline void SetBlockSizeBytes(int value) { m_blockSizeBytesHasBeenSet = true; m_blockSizeBytes = value; } /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline OrcSerDe& WithBlockSizeBytes(int value) { SetBlockSizeBytes(value); return *this;} /** *The number of rows between index entries. The default is 10,000 and the * minimum is 1,000.
*/ inline int GetRowIndexStride() const{ return m_rowIndexStride; } /** *The number of rows between index entries. The default is 10,000 and the * minimum is 1,000.
*/ inline bool RowIndexStrideHasBeenSet() const { return m_rowIndexStrideHasBeenSet; } /** *The number of rows between index entries. The default is 10,000 and the * minimum is 1,000.
*/ inline void SetRowIndexStride(int value) { m_rowIndexStrideHasBeenSet = true; m_rowIndexStride = value; } /** *The number of rows between index entries. The default is 10,000 and the * minimum is 1,000.
*/ inline OrcSerDe& WithRowIndexStride(int value) { SetRowIndexStride(value); return *this;} /** *Set this to true
to indicate that you want stripes to be padded
* to the HDFS block boundaries. This is useful if you intend to copy the data from
* Amazon S3 to HDFS before querying. The default is false
.
Set this to true
to indicate that you want stripes to be padded
* to the HDFS block boundaries. This is useful if you intend to copy the data from
* Amazon S3 to HDFS before querying. The default is false
.
Set this to true
to indicate that you want stripes to be padded
* to the HDFS block boundaries. This is useful if you intend to copy the data from
* Amazon S3 to HDFS before querying. The default is false
.
Set this to true
to indicate that you want stripes to be padded
* to the HDFS block boundaries. This is useful if you intend to copy the data from
* Amazon S3 to HDFS before querying. The default is false
.
A number between 0 and 1 that defines the tolerance for block padding as a * decimal fraction of stripe size. The default value is 0.05, which means 5 * percent of stripe size.
For the default values of 64 MiB ORC stripes and * 256 MiB HDFS blocks, the default block padding tolerance of 5 percent reserves a * maximum of 3.2 MiB for padding within the 256 MiB block. In such a case, if the * available size within the block is more than 3.2 MiB, a new, smaller stripe is * inserted to fit within that space. This ensures that no stripe crosses block * boundaries and causes remote reads within a node-local task.
Kinesis Data
* Firehose ignores this parameter when OrcSerDe$EnablePadding is
* false
.
A number between 0 and 1 that defines the tolerance for block padding as a * decimal fraction of stripe size. The default value is 0.05, which means 5 * percent of stripe size.
For the default values of 64 MiB ORC stripes and * 256 MiB HDFS blocks, the default block padding tolerance of 5 percent reserves a * maximum of 3.2 MiB for padding within the 256 MiB block. In such a case, if the * available size within the block is more than 3.2 MiB, a new, smaller stripe is * inserted to fit within that space. This ensures that no stripe crosses block * boundaries and causes remote reads within a node-local task.
Kinesis Data
* Firehose ignores this parameter when OrcSerDe$EnablePadding is
* false
.
A number between 0 and 1 that defines the tolerance for block padding as a * decimal fraction of stripe size. The default value is 0.05, which means 5 * percent of stripe size.
For the default values of 64 MiB ORC stripes and * 256 MiB HDFS blocks, the default block padding tolerance of 5 percent reserves a * maximum of 3.2 MiB for padding within the 256 MiB block. In such a case, if the * available size within the block is more than 3.2 MiB, a new, smaller stripe is * inserted to fit within that space. This ensures that no stripe crosses block * boundaries and causes remote reads within a node-local task.
Kinesis Data
* Firehose ignores this parameter when OrcSerDe$EnablePadding is
* false
.
A number between 0 and 1 that defines the tolerance for block padding as a * decimal fraction of stripe size. The default value is 0.05, which means 5 * percent of stripe size.
For the default values of 64 MiB ORC stripes and * 256 MiB HDFS blocks, the default block padding tolerance of 5 percent reserves a * maximum of 3.2 MiB for padding within the 256 MiB block. In such a case, if the * available size within the block is more than 3.2 MiB, a new, smaller stripe is * inserted to fit within that space. This ensures that no stripe crosses block * boundaries and causes remote reads within a node-local task.
Kinesis Data
* Firehose ignores this parameter when OrcSerDe$EnablePadding is
* false
.
The compression code to use over data blocks. The default is
* SNAPPY
.
The compression code to use over data blocks. The default is
* SNAPPY
.
The compression code to use over data blocks. The default is
* SNAPPY
.
The compression code to use over data blocks. The default is
* SNAPPY
.
The compression code to use over data blocks. The default is
* SNAPPY
.
The compression code to use over data blocks. The default is
* SNAPPY
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The column names for which you want Kinesis Data Firehose to create bloom
* filters. The default is null
.
The Bloom filter false positive probability (FPP). The lower the FPP, the * bigger the Bloom filter. The default value is 0.05, the minimum is 0, and the * maximum is 1.
*/ inline double GetBloomFilterFalsePositiveProbability() const{ return m_bloomFilterFalsePositiveProbability; } /** *The Bloom filter false positive probability (FPP). The lower the FPP, the * bigger the Bloom filter. The default value is 0.05, the minimum is 0, and the * maximum is 1.
*/ inline bool BloomFilterFalsePositiveProbabilityHasBeenSet() const { return m_bloomFilterFalsePositiveProbabilityHasBeenSet; } /** *The Bloom filter false positive probability (FPP). The lower the FPP, the * bigger the Bloom filter. The default value is 0.05, the minimum is 0, and the * maximum is 1.
*/ inline void SetBloomFilterFalsePositiveProbability(double value) { m_bloomFilterFalsePositiveProbabilityHasBeenSet = true; m_bloomFilterFalsePositiveProbability = value; } /** *The Bloom filter false positive probability (FPP). The lower the FPP, the * bigger the Bloom filter. The default value is 0.05, the minimum is 0, and the * maximum is 1.
*/ inline OrcSerDe& WithBloomFilterFalsePositiveProbability(double value) { SetBloomFilterFalsePositiveProbability(value); return *this;} /** *Represents the fraction of the total number of non-null rows. To turn off * dictionary encoding, set this fraction to a number that is less than the number * of distinct keys in a dictionary. To always use dictionary encoding, set this * threshold to 1.
*/ inline double GetDictionaryKeyThreshold() const{ return m_dictionaryKeyThreshold; } /** *Represents the fraction of the total number of non-null rows. To turn off * dictionary encoding, set this fraction to a number that is less than the number * of distinct keys in a dictionary. To always use dictionary encoding, set this * threshold to 1.
*/ inline bool DictionaryKeyThresholdHasBeenSet() const { return m_dictionaryKeyThresholdHasBeenSet; } /** *Represents the fraction of the total number of non-null rows. To turn off * dictionary encoding, set this fraction to a number that is less than the number * of distinct keys in a dictionary. To always use dictionary encoding, set this * threshold to 1.
*/ inline void SetDictionaryKeyThreshold(double value) { m_dictionaryKeyThresholdHasBeenSet = true; m_dictionaryKeyThreshold = value; } /** *Represents the fraction of the total number of non-null rows. To turn off * dictionary encoding, set this fraction to a number that is less than the number * of distinct keys in a dictionary. To always use dictionary encoding, set this * threshold to 1.
*/ inline OrcSerDe& WithDictionaryKeyThreshold(double value) { SetDictionaryKeyThreshold(value); return *this;} /** *The version of the file to write. The possible values are V0_11
* and V0_12
. The default is V0_12
.
The version of the file to write. The possible values are V0_11
* and V0_12
. The default is V0_12
.
The version of the file to write. The possible values are V0_11
* and V0_12
. The default is V0_12
.
The version of the file to write. The possible values are V0_11
* and V0_12
. The default is V0_12
.
The version of the file to write. The possible values are V0_11
* and V0_12
. The default is V0_12
.
The version of the file to write. The possible values are V0_11
* and V0_12
. The default is V0_12
.